Dynamic Bayesian networks for Arabic phonemes recognition

@article{Zarrouk2014DynamicBN,
  title={Dynamic Bayesian networks for Arabic phonemes recognition},
  author={Elyes Zarrouk and Yassine Ben Ayed and Fa{\"i}ez Gargouri},
  journal={2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)},
  year={2014},
  pages={480-485}
}
The majority of current automatic speech recognition systems uses a probabilistic modeling of the speech signal by hidden Markov models (HMM). In addition, the HMM are just a special case of graphical models which are dynamic Bayesian Networks (DBN). These are modeling tools more sophisticated because they allow to include several specific variables in the problem of automatic speech recognition other than the one used in HMM. The use of DBNs in speech recognition beyond has generated much… CONTINUE READING

Tables and Topics from this paper.